fundamentals of biometric analysis

8/4/2019 Fundamentals of Biometric Analysis

http://slidepdf.com/reader/full/fundamentals-of-biometric-analysis 1/19

FUNDAMENTALS OF

BIOMETRIC

ANALYSIS



What is biometrics?

Biometrics comprises methods for uniquely recognizing humans

based upon one or more intrinsic physical or behavioral traits.

Biometric characteristics can be divided into two main classes:

� Physiological -Related to the shape of the body.

Eg: Fingerprint, face recognition, DNA, hand and palm geometry,

iris recognition, odor/scent.� Behavioral ± Related to the behaviour of a person.

Eg: Typing rhythm, gait and voice.



Whether a human character can be used for biometric will depend

on the following parameters:

Universality- Each person should have the characteristic.

Uniqueness- Is how well the biometric separates individuals from one

another.

Permanence-Measures how well a biometric resists aging and other

variance over time.

Collectability- Ease of acquisition for measurement.

Performance- Accuracy, speed and robustness of technology used.

Acceptability- Degree of approval of a technology.

Curcumvention- Ease of use of a substitute.



OPERATI ON

A biometric system operates in the following two modes:

Verification: A one to one comparison of a captured

biometric with a stored template to verify that the

individual is who he claims to be. Can be done in

conjunction with a smart card, users name or ID

number.

Identification : A one to one comparison of the captured

biometric against a biometric database in attempt to

identify an unknown individual.



BASIC BLOCK DIAGRAM OF A BI OMETRIC

SYSTEM



Enrollment: The first time an individual uses a biometric

system is called enrollment.During enrollment biometric information from an individual

is stored.

In subsequent uses biometric information is detected and

compared.

The first block (sensor) is the interface between the real

world and the system, it has to acquire all the necessary data.

Most of the times it is an image acquisition system.



Second block performs all the necessary pre- processing: it has to remove artifacts from the

sensor, to enhance the input ( eg: removing

background noise), to use some kind of

normalization.

In the Third block features needed are extracted.

Correct features need to be extracted in an optimal way. A vector of numbers or an image with

particular properties is used to create a template.



� Template - template is a synthesis of the relevant characteristics

extracted from the source.- biometric measurements that are not used in the algorithm are

discarded in the template to reduce the file size.

- if enrollment is being performed the template is simply stored

somewhere.- if a matching phase is being performed the obtained template is

passed to a matcher that compares it with other existing

templates.

- the matching program will analyze the template with input. Thiswill then be output for any specified use or purpose.



PERF ORMANCE:The following are used as performance metrics for biometric systems:

False accept rate or false match rate ( FAR or FMR ) : the probability

that the system incorrectly matches the input pattern to a non-

matching template in the database. Measures the percent of invalid

inputs which are incorrectly accepted.

False reject rate or false non-match rate (FRR or FNMR) : the

probability that the system fails to detect a match between the input

pattern and a matching template in the database. It measures the percent of valid inputs which are incorrectly rejected.



PERF ORMANCE

Receiver operating characteristic or Relative operating

characteristic (ROC) - is a visual charactization of the trade-off

between the FAR and the FRR. In general, the matching algorithm

performs a decision based on a threshold which determines how

close to a template the input needs to be for it to be considered a

match. If the threshold is reduced, there will be less false non-

matches but more false accepts.

Equal error rate or crossover error rate (EER or CER) ± the rate at which both accept and reject errors are equal.



Failure to enroll rate (FTE or FER) ± the rate at which attempts to

create a template from an input is unsuccessful. This is most

commonly caused by low quality inputs.

Failure to capture rate (FTC) ± Within automatic systems, the

probability that the system fails to detect a biometric input when

presented correctly.

Template capacity ± the maximum number of sets of data which

can be stored in the system.



WHY USE BI OMETRICS?

� Only biometrics can verify you as you

� Tokens (smartcards, etc.) aren't you and can be:

± lost

± stolen

± duplicated (some)

± forgotten

� Passwords aren't you and can be:

± forgotten

± shared

± observed

± broken



Fingerprint Technology

� Local Features (Minutiae)

� Characteristics

± Type

± Orientation

± Spatial Frequency

± Curvature

± Position



Iris Technology

� Based on visible features, i.e. rings, furrows, freckles and the

corona� Iris essentially formed by 8 months of age and remains stable

through life

� Each iris has 266 unique spots vs. 13-60 for other biometrics

� Features and their location are used to form the IrisCodeT, whichis the digital template (512 bytes)



Face Technology

� Uses low cost off-the-shelf camera at low speed, low resolution

(3-5fps, 320x240)

� Several pictures taken at enrollment to allow for more accurate

searches

� All technologies emphasize facial features that are less

susceptible to alteration such as eye sockets, cheekbones, sides

of mouth

� Features extracted to form template (1300 bytes)



Voice Technology

� Voice recognition is not the same as speech recognition

� Considered physiological and behavioral

� Popular and low-cost, but less accurate and sometimes lengthy

enrollment

� Capable of working over the phone

± telephone banking

± password reset

± calling card security ± call center authentication (i.e. home alarm systems)

± probation/house arrest monitoring

� Many vendors; many proprietary technologies



Cultural & Social Issues

� In any large scenario some portion of the general population is

likely to be physiologically unable to use one or more technique.

� Some people have a concern for the physical effects of thetechnology upon them. This accounts for the greater acceptance

of newer iris recognition technology over the older retinal scan

technology.

� Religious and cultural concerns may also need to be

accommodated by organizations implementing biometric

technology. For example, certain cultures and religions prohibit

or look with great disfavor upon photographing of individuals.

fundamentals of biometric analysis

Documents